💲 LLM API Pricing
Chat per-token pricing plus image, video, speech, transcription and embedding rates — refreshed daily · updated 17h. Data: LiteLLM + OpenRouter, plus a small curated set (Kling, Hailuo, ElevenLabs, Cartesia) from official pricing pages.
All providersfireworks_ai 290bedrock 188bedrock_converse 152azure 133openrouter 100vercel_ai_gateway 95openai 93azure_ai 90novita 80deepinfra 68mistral 55gemini 51xai 44databricks 40
Cost calculator — what would your workload cost on each model?
| Model | Elo | Input $/M | Output $/M | Cache read | Cache write | Batch in/out | Context | History |
|---|---|---|---|---|---|---|---|---|
| claude-opus-4-1💬azure_ai | — | $15.0 | $75.0 | $1.50 | $18.8 | — | 200K | |
| claude-fable-5💬azure_ai | 1495 | $10.0 | $50.0 | $1.00 | $12.5 | — | 1.0M | |
| Meta-Llama-3.1-405B-Instructazure_ai | — | $5.33 | $16.0 | — | — | — | 128K | |
| claude-opus-4-7💬azure_ai | 1483 | $5.00 | $25.0 | $0.50 | $6.25 | — | 1.0M | |
| claude-opus-5💬azure_ai | — | $5.00 | $25.0 | $0.50 | $6.25 | — | 1.0M | |
| claude-opus-4-8💬azure_ai | 1452 | $5.00 | $25.0 | $0.50 | $6.25 | — | 1.0M | |
| gpt-5.5-2026-04-23azure_ai | — | $5.00 | $30.0 | $0.50 | — | — | 1.1M | |
| claude-opus-4-5💬azure_ai | — | $5.00 | $25.0 | $0.50 | $6.25 | — | 200K | |
| claude-opus-4-6💬azure_ai | 1497 | $5.00 | $25.0 | $0.50 | $6.25 | — | 1.0M | |
| gpt-5.5💬azure_ai | 1466 | $5.00 | $30.0 | $0.50 | — | — | 1.1M | |
| mistral-large💬azure_ai | — | $4.00 | $12.0 | — | — | — | 32K | |
| FW-Kimi-K3azure_ai | — | $3.30 | $16.5 | $0.33 | — | — | 1.0M | |
| claude-sonnet-4-5💬azure_ai | — | $3.00 | $15.0 | $0.30 | $3.75 | — | 200K | |
| claude-sonnet-4-6💬azure_ai | 1458 | $3.00 | $15.0 | $0.30 | $3.75 | — | 1.0M | |
| grok-4azure_ai | — | $3.00 | $15.0 | — | — | — | 131K | |
| grok-3azure_ai | — | $3.00 | $15.0 | — | — | — | 131K | |
| grok-3azure_ai | — | $3.00 | $15.0 | — | — | — | 131K | |
| Meta-Llama-3.1-70B-Instructazure_ai | — | $2.68 | $3.54 | — | — | — | 128K | |
| gpt-5.4💬azure_ai | 1453 | $2.50 | $15.0 | $0.25 | — | — | 1.1M | |
| gpt-5.4-2026-03-05azure_ai | — | $2.50 | $15.0 | $0.25 | — | — | 1.1M | |
| FW-GLM-5.2-Fastazure_ai | — | $2.10 | $6.60 | $0.21 | — | — | 1.0M | |
| Llama-3.2-90B-Vision-Instructazure_ai | — | $2.04 | $2.04 | — | — | — | 128K | |
| mistral-large-2407💬azure_ai | 1266 | $2.00 | $6.00 | — | — | — | 128K | |
| mistral-large-latestazure_ai | — | $2.00 | $6.00 | — | — | — | 128K | |
| claude-sonnet-5💬azure_ai | — | $2.00 | $10.0 | $0.20 | $2.50 | — | 1.0M | |
| FW-DeepSeek-V4-Proazure_ai | — | $1.93 | $3.83 | $0.17 | — | — | 1.0M | |
| deepseek-v4-pro💬azure_ai | 1451 | $1.74 | $3.48 | — | — | — | 1.0M | |
| FW-GLM-5.2azure_ai | — | $1.54 | $4.84 | $0.15 | — | — | 1.0M | |
| FW-GLM-5.1azure_ai | — | $1.54 | $4.84 | $0.29 | — | — | 203K | |
| Llama-4-Maverick-17B-128E-Instruct-FP8azure_ai | — | $1.41 | $0.35 | — | — | — | 1.0M | |
| MAI-DS-R1azure_ai | — | $1.35 | $5.40 | — | — | — | 128K | |
| deepseek-r1🧮azure_ai | 1373 | $1.35 | $5.40 | — | — | — | 128K | |
| grok-4.3💬azure_ai | 1398 | $1.25 | $2.50 | $0.20 | — | — | 200K | |
| deepseek-v3.1azure_ai | — | $1.23 | $4.94 | — | — | — | 131K | |
| deepseek-v3azure_ai | — | $1.14 | $4.56 | — | — | — | 128K | |
| deepseek-v3-0324azure_ai | — | $1.14 | $4.56 | — | — | — | 128K | |
| Meta-Llama-3-70B-Instructazure_ai | — | $1.10 | $0.37 | — | — | — | 8K | |
| FW-GLM-5azure_ai | — | $1.10 | $3.52 | $0.22 | — | — | 200K | |
| FW-Kimi-K2.7-Codeazure_ai | — | $1.05 | $4.40 | $0.21 | — | — | 262K | |
| FW-Kimi-K2.6azure_ai | — | $1.04 | $4.40 | $0.18 | — | — | 262K | |
| claude-haiku-4-5💬azure_ai | — | $1.00 | $5.00 | $0.10 | $1.25 | — | 200K | |
| mistral-smallazure_ai | — | $1.00 | $3.00 | — | — | — | 32K | |
| FW-Inklingazure_ai | — | $1.00 | $4.05 | $0.17 | — | — | 1.0M | |
| kimi-k2.6💬azure_ai | 1455 | $0.95 | $4.00 | — | — | — | 262K | |
| gpt-5.4-mini💬azure_ai | — | $0.75 | $4.50 | $0.0750 | — | — | 272K | |
| gpt-5.4-mini-2026-03-17azure_ai | — | $0.75 | $4.50 | $0.0750 | — | — | 272K | |
| Llama-3.3-70B-Instruct💬azure_ai | 1275 | $0.71 | $0.71 | — | — | — | 128K | |
| FW-Kimi-K2.5azure_ai | — | $0.66 | $3.30 | $0.11 | — | — | 262K | |
| FW-DeepSeek-V3.2azure_ai | — | $0.62 | $1.85 | $0.31 | — | — | 164K | |
| FW-Nemotron-3-Ultra-NVFP4azure_ai | — | $0.60 | $2.40 | $0.12 | — | — | 262K |
Recent price changes
- ▲ 10.0%Mistral: Devstral 2 2512mistralai · output $2.00 → $2.2012h
- ▲ 10.0%Mistral: Devstral 2 2512mistralai · input $0.40 → $0.4412h
- ▲ 33.3%MoonshotAI: Kimi K2.5moonshotai · output $2.25 → $3.0012h
- ▲ 33.3%MoonshotAI: Kimi K2.5moonshotai · input $0.45 → $0.6012h
- ▲ 25.0%MiniMax: MiniMax M2.7minimax · output $0.96 → $1.2012h
- ▲ 25.0%MiniMax: MiniMax M2.7minimax · input $0.24 → $0.3012h
- ▲ 30.4%Z.ai: GLM 5.1z-ai · output $3.04 → $3.9612h
- ▲ 30.4%Z.ai: GLM 5.1z-ai · input $0.97 → $1.2612h
- ▲ 54.4%DeepSeek: DeepSeek V4 Flash 0423deepseek · output $0.11 → $0.1812h
- ▲ 54.4%DeepSeek: DeepSeek V4 Flash 0423deepseek · input $0.0574 → $0.088612h
- ▲ 50.2%DeepSeek: DeepSeek V4 Pro 0423deepseek · output $1.05 → $1.5812h
- ▲ 50.2%DeepSeek: DeepSeek V4 Pro 0423deepseek · input $0.53 → $0.7912h
- ▲ 7.7%MoonshotAI Kimi Latestmoonshotai · output $13.0 → $14.012h
- ▲ 7.7%MoonshotAI Kimi Latestmoonshotai · input $2.60 → $2.8012h
- ▲ 23.2%Z.ai: GLM 5.2z-ai · output $3.04 → $3.7412h
- ▼ 12.5%DeepSeek V4 Flash Latestdeepseek · input $0.0400 → $0.035012h
- ▼ 6.3%DeepSeek V4 Flash Latestdeepseek · output $0.0800 → $0.075012h
- ▼ 5.0%Thinking Machines: Inklingthinkingmachines · input $1.00 → $0.9512h
- ▲ 23.2%Z.ai: GLM 5.2z-ai · input $0.97 → $1.1912h
- ▼ 27.3%DeepSeek V4 Flash Latestdeepseek · input $0.0550 → $0.04001d
Price cuts are green — they make AI cheaper for everyone.